© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25141
    Prev
    Next
    INDEX
    Explanations

    getting this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    以ä¸ĭåĨħ容
    -0.07
    æĮĿ
    -0.07
    presso
    -0.07
    fac
    -0.07
    <tag
    -0.07
    òa
    -0.07
     Fac
    -0.07
    tit
    -0.07
    uze
    -0.07
    åħµçļĦ
    -0.06
    POSITIVE LOGITS
    ä¸Ĭè¿°
    0.08
    ä¸ĩåį·
    0.07
     aforementioned
    0.07
    antha
    0.07
    §
    0.07
    è§Ħå®ļçļĦ
    0.06
    åīįè¿°
    0.06
    èIJ½
    0.06
    æĹłæķĮ
    0.06
    åħļæĶ¿æľºåħ³
    0.06
    Activations Density 0.179%

    No Known Activations